@josstei/maestro 1.6.4-rc.1

package/agents/refactor.md

@@ -0,0 +1,22 @@
+---
+name: refactor
+kind: local
+description: "Refactoring specialist for codebase modernization, structural improvements, and technical debt reduction. Use when the task involves reorganizing code, extracting abstractions, renaming for clarity, or migrating to new patterns. For example: extracting a service layer, converting callbacks to async/await, or splitting a monolithic module."
+tools:
+  - read_file
+  - list_directory
+  - glob
+  - grep_search
+  - write_file
+  - replace
+  - run_shell_command
+  - write_todos
+  - activate_skill
+  - read_many_files
+  - ask_user
+temperature: 0.2
+max_turns: 25
+timeout_mins: 10
+---
+
+Agent methodology loaded via MCP tool `get_agent`. Call `get_agent(agents: ["refactor"])` to read the full methodology at delegation time.

package/agents/release_manager.md

@@ -0,0 +1,22 @@
+---
+name: release_manager
+kind: local
+description: "Release management specialist for release notes, changelogs, version bumps, release checklists, and rollout coordination. Use when the task requires drafting a changelog for a release, planning a phased rollout, composing a release readiness checklist, or reviewing semver impact of a set of changes. For example: producing release notes from commit history, planning a canary rollout, or reviewing a breaking-change label."
+tools:
+  - read_file
+  - list_directory
+  - glob
+  - grep_search
+  - write_file
+  - replace
+  - read_many_files
+  - google_web_search
+  - write_todos
+  - ask_user
+  - web_fetch
+temperature: 0.3
+max_turns: 15
+timeout_mins: 5
+---
+
+Agent methodology loaded via MCP tool `get_agent`. Call `get_agent(agents: ["release-manager"])` to read the full methodology at delegation time.

package/agents/security_engineer.md

@@ -0,0 +1,21 @@
+---
+name: security_engineer
+kind: local
+description: "Security engineering specialist for vulnerability assessment, threat modeling, and security best practices. Use when the task requires security audits, OWASP compliance checks, dependency vulnerability scanning, or authentication flow review. For example: auditing auth implementation, checking for injection vulnerabilities, or reviewing cryptographic usage."
+tools:
+  - read_file
+  - list_directory
+  - glob
+  - grep_search
+  - run_shell_command
+  - google_web_search
+  - read_many_files
+  - web_fetch
+  - write_todos
+  - ask_user
+temperature: 0.2
+max_turns: 20
+timeout_mins: 8
+---
+
+Agent methodology loaded via MCP tool `get_agent`. Call `get_agent(agents: ["security-engineer"])` to read the full methodology at delegation time.

package/agents/seo_specialist.md

@@ -0,0 +1,21 @@
+---
+name: seo_specialist
+kind: local
+description: "SEO specialist for technical audits, meta tag optimization, schema markup, and crawlability analysis. Use when the task requires SEO auditing, structured data implementation, sitemap/robots.txt review, or Core Web Vitals optimization. For example: auditing a site's crawlability, implementing JSON-LD schema markup, or optimizing meta tag strategy."
+tools:
+  - read_file
+  - list_directory
+  - glob
+  - grep_search
+  - run_shell_command
+  - google_web_search
+  - web_fetch
+  - write_todos
+  - read_many_files
+  - ask_user
+temperature: 0.2
+max_turns: 20
+timeout_mins: 8
+---
+
+Agent methodology loaded via MCP tool `get_agent`. Call `get_agent(agents: ["seo-specialist"])` to read the full methodology at delegation time.

package/agents/site_reliability_engineer.md

@@ -0,0 +1,21 @@
+---
+name: site_reliability_engineer
+kind: local
+description: "Site reliability engineering specialist for SLOs, error budgets, capacity planning, runbooks, and postmortems. Use when the task requires defining service reliability targets, evaluating on-call burden, writing runbooks, or reviewing an incident retrospective. For example: defining SLIs/SLOs for a new service, auditing an existing error budget policy, or drafting a runbook for a known failure mode."
+tools:
+  - read_file
+  - list_directory
+  - glob
+  - grep_search
+  - run_shell_command
+  - google_web_search
+  - read_many_files
+  - write_todos
+  - ask_user
+  - web_fetch
+temperature: 0.2
+max_turns: 20
+timeout_mins: 8
+---
+
+Agent methodology loaded via MCP tool `get_agent`. Call `get_agent(agents: ["site-reliability-engineer"])` to read the full methodology at delegation time.

package/agents/solutions_architect.md

@@ -0,0 +1,19 @@
+---
+name: solutions_architect
+kind: local
+description: "Solutions architecture specialist for enterprise integration patterns, vendor systems, cross-team architecture, and target-state design. Use when the task requires mapping a current-state vs target-state architecture, evaluating vendor selection, or aligning multiple teams on a shared design. For example: designing an integration between SAP and a new CRM, mapping a strangler-fig path from monolith to services, or producing an ADR for a cross-organization capability."
+tools:
+  - read_file
+  - list_directory
+  - glob
+  - grep_search
+  - google_web_search
+  - read_many_files
+  - ask_user
+  - web_fetch
+temperature: 0.3
+max_turns: 15
+timeout_mins: 5
+---
+
+Agent methodology loaded via MCP tool `get_agent`. Call `get_agent(agents: ["solutions-architect"])` to read the full methodology at delegation time.

package/agents/technical_writer.md

@@ -0,0 +1,21 @@
+---
+name: technical_writer
+kind: local
+description: "Technical writing specialist for documentation, API references, and architectural diagrams. Use when the task requires writing README files, API documentation, architecture decision records, or inline documentation. For example: writing an OpenAPI description, creating a getting-started guide, or documenting module interfaces."
+tools:
+  - read_file
+  - list_directory
+  - glob
+  - grep_search
+  - write_file
+  - replace
+  - read_many_files
+  - google_web_search
+  - ask_user
+  - write_todos
+temperature: 0.3
+max_turns: 15
+timeout_mins: 5
+---
+
+Agent methodology loaded via MCP tool `get_agent`. Call `get_agent(agents: ["technical-writer"])` to read the full methodology at delegation time.

package/agents/tester.md

@@ -0,0 +1,23 @@
+---
+name: tester
+kind: local
+description: "Testing specialist for unit tests, integration tests, test coverage analysis, and TDD workflows. Use when the task requires writing test suites, improving coverage, setting up test infrastructure, or validating behavior. For example: writing unit tests for a service class, setting up integration test fixtures, or creating end-to-end test scenarios."
+tools:
+  - read_file
+  - list_directory
+  - glob
+  - grep_search
+  - write_file
+  - replace
+  - run_shell_command
+  - write_todos
+  - activate_skill
+  - read_many_files
+  - ask_user
+  - google_web_search
+temperature: 0.2
+max_turns: 25
+timeout_mins: 10
+---
+
+Agent methodology loaded via MCP tool `get_agent`. Call `get_agent(agents: ["tester"])` to read the full methodology at delegation time.

package/agents/ux_designer.md

@@ -0,0 +1,20 @@
+---
+name: ux_designer
+kind: local
+description: "UX designer for user flow design, interaction patterns, wireframe descriptions, and usability evaluation. Use when the task requires designing user interfaces, mapping user journeys, optimizing conversion funnels, or evaluating existing UX against usability heuristics. For example: designing an onboarding flow, wireframing a dashboard layout, or auditing checkout abandonment."
+tools:
+  - read_file
+  - list_directory
+  - glob
+  - grep_search
+  - write_file
+  - replace
+  - google_web_search
+  - read_many_files
+  - ask_user
+temperature: 0.2
+max_turns: 20
+timeout_mins: 8
+---
+
+Agent methodology loaded via MCP tool `get_agent`. Call `get_agent(agents: ["ux-designer"])` to read the full methodology at delegation time.

package/agents/zos_sysprog.md

@@ -0,0 +1,21 @@
+---
+name: zos_sysprog
+kind: local
+description: "z/OS systems programming specialist for JCL, USS, SMP/E, RACF, subsystem diagnostics, and batch scheduling. Use when the task requires JCL authoring or review, z/OS Unix System Services setup, SMP/E maintenance, RACF profile review, or diagnosing SYSLOG/OPERLOG issues. For example: writing a JCL restart procedure, planning an SMP/E PTF install, or reviewing RACF dataset profiles for least privilege."
+tools:
+  - read_file
+  - list_directory
+  - glob
+  - grep_search
+  - run_shell_command
+  - google_web_search
+  - read_many_files
+  - write_todos
+  - ask_user
+  - web_fetch
+temperature: 0.2
+max_turns: 20
+timeout_mins: 8
+---
+
+Agent methodology loaded via MCP tool `get_agent`. Call `get_agent(agents: ["zos-sysprog"])` to read the full methodology at delegation time.

package/bin/maestro-mcp-server.js

@@ -0,0 +1,10 @@
+#!/usr/bin/env node
+'use strict';
+
+const path = require('node:path');
+
+process.env.MAESTRO_RUNTIME = process.env.MAESTRO_RUNTIME || 'codex';
+process.env.MAESTRO_EXTENSION_PATH =
+  process.env.MAESTRO_EXTENSION_PATH || path.resolve(__dirname, '..');
+
+require('../src/mcp/maestro-server').main();

package/claude/.claude-plugin/plugin.json

@@ -0,0 +1,21 @@
+{
+  "name": "maestro",
+  "version": "1.6.4-rc.1",
+  "description": "Multi-agent development orchestration platform — 39 specialists, 4-phase orchestration, native parallel subagents, persistent sessions, and standalone review/debug/security/perf/seo/a11y/compliance commands",
+  "author": {
+    "name": "josstei",
+    "email": "hello@josstei.dev",
+    "url": "https://github.com/josstei"
+  },
+  "license": "Apache-2.0",
+  "hooks": "./hooks/claude-hooks.json",
+  "mcpServers": "./.mcp.json",
+  "homepage": "https://github.com/josstei/maestro-orchestrate",
+  "repository": "https://github.com/josstei/maestro-orchestrate",
+  "keywords": [
+    "orchestration",
+    "multi-agent",
+    "planning",
+    "execution"
+  ]
+}

package/claude/.mcp.json

@@ -0,0 +1,11 @@
+{
+  "mcpServers": {
+    "maestro": {
+      "command": "node",
+      "args": [
+        "${CLAUDE_PLUGIN_ROOT}/mcp/maestro-server.js"
+      ],
+      "cwd": "${CLAUDE_PLUGIN_ROOT}"
+    }
+  }
+}

package/claude/README.md

@@ -0,0 +1,191 @@
+# Maestro — Claude Code Plugin
+
+[![Version](https://img.shields.io/badge/version-1.6.4-blue)](https://github.com/josstei/maestro-orchestrate/releases)
+[![License](https://img.shields.io/badge/license-Apache-2.0-green)](LICENSE)
+[![Claude Code](https://img.shields.io/badge/Claude_Code-plugin-orange)](https://docs.anthropic.com/en/docs/claude-code)
+
+Multi-agent development orchestration platform — 39 specialists, 4-phase orchestration, native parallel subagents, persistent sessions, and standalone review/debug/security/perf/seo/a11y/compliance commands
+
+## Installation
+
+### From Marketplace (recommended)
+
+Add the maestro marketplace, then install the plugin:
+
+```bash
+claude plugin marketplace add josstei/maestro-orchestrate
+claude plugin install maestro@maestro-orchestrator --scope user
+```
+
+### Installation Scopes
+
+| Scope | Flag | Effect |
+|-------|------|--------|
+| User (default) | `--scope user` | Available across all your projects |
+| Project | `--scope project` | Shared with your team via version control |
+| Local | `--scope local` | Project-specific, gitignored |
+
+### Plugin Management
+
+```bash
+claude plugin update maestro          # Pull the latest version
+claude plugin disable maestro         # Disable without uninstalling
+claude plugin uninstall maestro       # Remove the plugin entirely
+```
+
+### Development / Testing
+
+Load the plugin for a single session without persistent registration:
+
+```bash
+claude --plugin-dir /path/to/maestro-orchestrate/claude
+```
+
+Use `/reload-plugins` inside the session to pick up file changes without restarting.
+
+For local development, clone the repo first:
+
+```bash
+git clone https://github.com/josstei/maestro-orchestrate
+claude --plugin-dir /path/to/maestro-orchestrate/claude
+```
+
+### Verify Installation
+
+After starting Claude Code with the plugin loaded:
+
+- Type `/` and verify `orchestrate`, `review-code`, `debug-workflow`, `security-audit`, `perf-check`, `seo-audit`, `a11y-audit`, and `compliance-check` appear in autocomplete.
+- Run `/agents` and verify agents with the `maestro:` prefix appear (e.g., `maestro:coder`, `maestro:architect`).
+- Confirm MCP tools are registered: `mcp__plugin_maestro_maestro__*` tools should be available (e.g., `mcp__plugin_maestro_maestro__get_session_status`).
+
+### MCP Server
+
+The MCP server is auto-registered via `claude/.mcp.json`. If MCP tools are not available, verify the `.mcp.json` file exists at the plugin root:
+
+```json
+{
+  "mcpServers": {
+    "maestro": {
+      "command": "node",
+      "args": ["${CLAUDE_PLUGIN_ROOT}/mcp/maestro-server.js"],
+      "cwd": "${CLAUDE_PLUGIN_ROOT}"
+    }
+  }
+}
+```
+
+**Note:** Claude is filesystem-backed for shared MCP content. Published Claude bundles carry a generated local `src/` payload derived from the canonical source tree, and shared skills, templates, references, and delegation protocols are loaded from that local payload through `get_skill_content`. Runtime-local `SKILL.md` files remain only where Claude needs on-disk discovery stubs or public entry points.
+
+## Quick Start
+
+Start a full orchestration by describing what you want to build:
+
+```
+/orchestrate Build a REST API for a task management system with user authentication
+```
+
+Maestro will walk you through the complete lifecycle:
+
+1. **Design Dialogue** -- Structured questions one at a time, 2-3 architectural approaches with trade-offs.
+2. **Design Review** -- Section-by-section approval of the design document.
+3. **Implementation Planning** -- Phase breakdown, agent assignments, dependency graph, parallel execution opportunities.
+4. **Execution Mode Selection** -- Parallel or sequential dispatch.
+5. **Phase-by-Phase Execution** -- Specialized agents implement the plan with session state updates after each phase.
+6. **Quality Gate** -- Final code review blocks on unresolved Critical or Major findings.
+7. **Completion & Archival** -- Summary of files changed, token usage, and next steps.
+
+**Express mode** -- For simple tasks, Maestro detects low complexity and uses a streamlined flow: 1-2 questions, brief approval, single agent, code review, done.
+
+## Commands
+
+| Command | Purpose |
+|---------|---------|
+| `/orchestrate` | Full orchestration workflow (design, plan, execute, complete) |
+| `/execute` | Execute an approved implementation plan |
+| `/status` | Display current session status |
+| `/resume-session` | Resume an interrupted session |
+| `/archive` | Archive the active session |
+| `/review-code` | Standalone code review |
+| `/debug-workflow` | Standalone debugging session |
+| `/security-audit` | Standalone security assessment |
+| `/perf-check` | Standalone performance analysis |
+| `/seo-audit` | Standalone SEO assessment |
+| `/a11y-audit` | Standalone accessibility audit |
+| `/compliance-check` | Standalone compliance review |
+
+These Claude entrypoints come from the public top-level skills in `skills/`. Internal methodology skills remain hidden with `user-invocable: false`.
+
+## Agents
+
+All agents are registered with a `maestro:` namespace prefix. When the orchestrator delegates work, it dispatches agents as `maestro:coder`, `maestro:architect`, etc. Claude Code agents use **kebab-case** naming (e.g., `code-reviewer`, `api-designer`), contrasting with Gemini CLI's snake_case convention (e.g., `code_reviewer`, `api_designer`). The `maestro:` prefix is always required when dispatching.
+
+All agents share a baseline tool set: `Read`, `Glob`, `Grep`, `Skill`. Tool tiers reflect additional capabilities beyond that baseline.
+
+| Agent | Domain | Specialization | Tool Tier |
+|-------|--------|----------------|-----------|
+| accessibility-specialist | Design | WCAG compliance auditing, ARIA review | Read + Shell |
+| analytics-engineer | Analytics | Event tracking, conversion funnels | Full Access |
+| api-designer | Engineering | API contracts and endpoint design | Read-Only |
+| architect | Engineering | System design and architecture decisions | Read-Only |
+| cloud-architect | Platform | AWS/GCP/Azure topology, IaC, multi-region design | Read-Only |
+| cobol-engineer | Mainframe | Mainframe COBOL, JCL, CICS/IMS on z/OS | Full Access |
+| code-reviewer | Engineering | Code quality review and bug identification | Read-Only |
+| coder | Engineering | Feature implementation | Full Access |
+| compliance-reviewer | Compliance | Legal and regulatory compliance (GDPR, CCPA, licensing) | Read-Only |
+| content-strategist | Content | Content planning and strategy | Read-Only |
+| copywriter | Content | Marketing copy and landing-page content | Read + Write |
+| data-engineer | Engineering | Schema design, queries, and data pipelines | Full Access |
+| database-administrator | Engineering | RDBMS tuning, indexes, migration safety (Postgres, MySQL, Oracle, SQL Server) | Read + Shell |
+| db2-dba | Mainframe | DB2 for z/OS and LUW, REORG, RUNSTATS, bind/rebind | Read + Shell |
+| debugger | Engineering | Root cause analysis and defect investigation | Read + Shell |
+| design-system-engineer | Design | Design tokens and theming | Full Access |
+| devops-engineer | Engineering | CI/CD, containerization, and deployment | Full Access |
+| hlasm-assembler-specialist | Mainframe | IBM HLASM for z/OS, macros, SVCs | Full Access |
+| i18n-specialist | Internationalization | Internationalization and locale management | Full Access |
+| ibm-i-specialist | Mainframe | IBM i RPG/CL, DB2 for i, OS/400 | Full Access |
+| integration-engineer | Platform | B2B APIs, ETL, message brokers (Kafka, MQ) | Full Access |
+| ml-engineer | ML/AI | Model training, feature pipelines, evaluation | Full Access |
+| mlops-engineer | ML/AI | Model registry, CI/CD for models, drift detection | Full Access |
+| mobile-engineer | Engineering | iOS/Android/React Native/Flutter platform work | Full Access |
+| observability-engineer | Ops | Metrics, logs, traces, OpenTelemetry, dashboards | Full Access |
+| performance-engineer | Engineering | Performance profiling and optimization | Read + Shell |
+| platform-engineer | Platform | Internal developer platforms, paved paths | Full Access |
+| product-manager | Product | Requirements and product strategy | Read + Write |
+| prompt-engineer | ML/AI | LLM prompt design, few-shot, RAG tuning | Read + Write |
+| refactor | Engineering | Structural refactoring and technical debt | Full Access |
+| release-manager | Ops | Release notes, changelogs, rollout planning | Read + Write |
+| security-engineer | Engineering | Security assessment and vulnerability analysis | Read + Shell |
+| seo-specialist | SEO | Technical SEO auditing and structured data | Read + Shell |
+| site-reliability-engineer | Ops | SLOs, error budgets, runbooks, postmortems | Read + Shell |
+| solutions-architect | Platform | Enterprise integration, cross-team architecture | Read-Only |
+| technical-writer | Engineering | Documentation and technical writing | Read + Write |
+| tester | Engineering | Test implementation and coverage analysis | Full Access |
+| ux-designer | Design | User experience design | Read + Write |
+| zos-sysprog | Mainframe | z/OS systems programming, JCL, USS, RACF | Read + Shell |
+
+## Claude Code Specifics
+
+### MCP Tool Names
+
+MCP tools are registered with a namespace prefix. Skills reference bare names like `initialize_workspace` but the actual tool name is `mcp__plugin_maestro_maestro__initialize_workspace`. The orchestrate skill includes a mapping table that handles this automatically.
+
+### Agent Names
+
+Agents are registered as `maestro:<agent-name>` (e.g., `maestro:coder`, `maestro:code-reviewer`). The orchestrate skill includes a mapping that handles this automatically.
+
+### Hooks
+
+Claude Code hooks are registered in `hooks/claude-hooks.json`:
+
+- **SessionStart** — Prune stale sessions, initialize hook state
+- **SessionEnd** — Clean up hook state
+- **PreToolUse (Agent matcher)** — Track active agent, inject session context
+- **PreToolUse (Bash matcher)** — Policy enforcement (blocks destructive commands)
+
+## Configuration
+
+Supported settings include `MAESTRO_STATE_DIR`, `MAESTRO_DISABLED_AGENTS`, `MAESTRO_EXECUTION_MODE`, `MAESTRO_VALIDATION_STRICTNESS`, `MAESTRO_AUTO_ARCHIVE`, `MAESTRO_MAX_RETRIES`, and `MAESTRO_MAX_CONCURRENT`. Claude-specific runtime paths come from `CLAUDE_PLUGIN_ROOT` and `CLAUDE_PROJECT_DIR`.
+
+## License
+
+Apache-2.0

package/claude/agents/accessibility-specialist.md

@@ -0,0 +1,36 @@
+---
+name: accessibility-specialist
+description: |
+  Accessibility specialist for WCAG compliance auditing, ARIA implementation review, keyboard navigation testing, and inclusive design assessment. Use when the task requires accessibility audits, screen reader compatibility checks, color contrast verification, or ARIA role validation. For example: auditing a web app for WCAG 2.1 AA compliance, reviewing keyboard navigation in modal dialogs, or validating ARIA usage in custom components.
+  
+  <example>
+  Context: User needs a WCAG accessibility audit.
+  user: "Audit our web app for WCAG 2.1 AA compliance"
+  assistant: "I'll systematically audit against all WCAG 2.1 AA success criteria: perceivable (alt text, contrast, captions), operable (keyboard, timing), understandable (readability, predictability), and robust (parsing, ARIA)."
+  <commentary>
+  Accessibility Specialist handles WCAG compliance auditing — read-only + shell for a11y tools.
+  </commentary>
+  </example>
+  <example>
+  Context: User needs keyboard navigation review.
+  user: "Check if our modal dialogs and dropdown menus are keyboard accessible"
+  assistant: "I'll review focus management, tab order, escape key handling, and ARIA roles for each interactive component, providing specific remediation patterns."
+  <commentary>
+  Accessibility Specialist handles keyboard accessibility and ARIA implementation review.
+  </commentary>
+  </example>
+model: inherit
+color: violet
+maxTurns: 20
+tools:
+  - Read
+  - Bash
+  - Glob
+  - Grep
+  - WebSearch
+  - TaskCreate
+  - TaskUpdate
+  - TaskList
+---
+
+Agent methodology loaded via MCP tool `get_agent`. Call `get_agent(agents: ["accessibility-specialist"])` to read the full methodology at delegation time.

package/claude/agents/analytics-engineer.md

@@ -0,0 +1,38 @@
+---
+name: analytics-engineer
+description: |
+  Analytics engineering specialist for event tracking implementation, analytics schemas, conversion funnels, A/B test design, and measurement planning. Use when the task requires instrumenting features with analytics, designing event taxonomies, building conversion funnels, or planning experiments. For example: adding event tracking to a checkout flow, designing an A/B test for a pricing page, or defining KPI dashboards.
+  
+  <example>
+  Context: User needs to instrument a feature with analytics tracking.
+  user: "Add event tracking to our checkout flow to measure conversion funnel"
+  assistant: "I'll design the event taxonomy for the checkout funnel, implement tracking calls at each step, and validate data collection with test events."
+  <commentary>
+  Analytics Engineer handles tracking implementation and event schema design.
+  </commentary>
+  </example>
+  <example>
+  Context: User needs A/B test design for a feature experiment.
+  user: "Design an A/B test for our new pricing page layout"
+  assistant: "I'll define test hypotheses, calculate sample size for statistical significance, design event tracking for both variants, and specify success metrics."
+  <commentary>
+  Analytics Engineer handles experiment design and measurement planning.
+  </commentary>
+  </example>
+model: inherit
+color: olive
+maxTurns: 25
+tools:
+  - Read
+  - Write
+  - Edit
+  - Bash
+  - Glob
+  - Grep
+  - WebSearch
+  - TaskCreate
+  - TaskUpdate
+  - TaskList
+---
+
+Agent methodology loaded via MCP tool `get_agent`. Call `get_agent(agents: ["analytics-engineer"])` to read the full methodology at delegation time.

package/claude/agents/api-designer.md

@@ -0,0 +1,33 @@
+---
+name: api-designer
+description: |
+  API design specialist for endpoint design, request/response contracts, and API versioning strategies. Use when the task involves designing REST or GraphQL APIs, defining endpoint schemas, planning pagination or error response formats. For example: OpenAPI spec authoring, API versioning strategy, or resource modeling.
+  
+  <example>
+  Context: User needs REST or GraphQL API contracts designed.
+  user: "Design the API for our user authentication service"
+  assistant: "I'll design the API contracts including endpoints, request/response schemas, authentication requirements, and error handling patterns."
+  <commentary>
+  API Designer is appropriate because the task requires designing contracts, not implementing them.
+  </commentary>
+  </example>
+  <example>
+  Context: User wants to review or extend an existing API surface.
+  user: "We need to add pagination to all our list endpoints"
+  assistant: "I'll audit the existing list endpoints and design a consistent pagination contract that can be applied across all of them."
+  <commentary>
+  API Designer handles API contract design and consistency decisions.
+  </commentary>
+  </example>
+model: inherit
+color: cyan
+maxTurns: 15
+tools:
+  - Read
+  - Glob
+  - Grep
+  - WebSearch
+  - WebFetch
+---
+
+Agent methodology loaded via MCP tool `get_agent`. Call `get_agent(agents: ["api-designer"])` to read the full methodology at delegation time.

package/claude/agents/architect.md

@@ -0,0 +1,33 @@
+---
+name: architect
+description: |
+  System design specialist for architecture decisions, technology selection, and high-level component design. Use when the task requires evaluating architectural trade-offs, designing system components, selecting technology stacks, or planning service boundaries. For example: microservice decomposition, database schema design, or API contract planning.
+  
+  <example>
+  Context: User needs to design a new system or evaluate architectural trade-offs.
+  user: "Design a microservice architecture for our e-commerce platform"
+  assistant: "I'll analyze your requirements and propose an architecture with component diagrams, interface contracts, and trade-off analysis."
+  <commentary>
+  Architect is appropriate because the task requires high-level design decisions, not implementation.
+  </commentary>
+  </example>
+  <example>
+  Context: User is selecting technology stacks or evaluating options.
+  user: "Should we use PostgreSQL or MongoDB for our user data?"
+  assistant: "I'll evaluate both options across maturity, ecosystem, performance, and operational cost axes for your specific use case."
+  <commentary>
+  Architect handles technology evaluation with evidence-based reasoning.
+  </commentary>
+  </example>
+model: inherit
+color: blue
+maxTurns: 15
+tools:
+  - Read
+  - Glob
+  - Grep
+  - WebSearch
+  - WebFetch
+---
+
+Agent methodology loaded via MCP tool `get_agent`. Call `get_agent(agents: ["architect"])` to read the full methodology at delegation time.

package/claude/agents/cloud-architect.md

@@ -0,0 +1,33 @@
+---
+name: cloud-architect
+description: |
+  Cloud architecture specialist for AWS, GCP, and Azure topology design, IaC patterns, multi-region resilience, and cost/security trade-offs. Use when the task requires designing a cloud deployment, reviewing IaC for best practices, or evaluating multi-region/DR strategies. For example: choosing between ECS and EKS, designing a VPC topology, or evaluating a CDN/edge-compute strategy.
+  
+  <example>
+  Context: User needs a cloud topology designed or reviewed.
+  user: "Design the AWS topology for our multi-tenant SaaS with per-tenant isolation"
+  assistant: "I'll propose a landing-zone layout, per-tenant account/VPC isolation pattern, shared-services account, and tenant-lifecycle operations, with cost and blast-radius trade-offs."
+  <commentary>
+  Cloud Architect is appropriate for topology design and trade-off analysis; it does not write IaC.
+  </commentary>
+  </example>
+  <example>
+  Context: User needs an IaC review for best practices.
+  user: "Review our Terraform modules for security and cost risks"
+  assistant: "I'll audit state handling, IAM least-privilege, tagging, data perimeter, and cost levers (autoscaling, spot, right-sizing), and list findings by severity."
+  <commentary>
+  Cloud Architect handles IaC pattern review, read-only.
+  </commentary>
+  </example>
+model: inherit
+color: sky
+maxTurns: 15
+tools:
+  - Read
+  - Glob
+  - Grep
+  - WebSearch
+  - WebFetch
+---
+
+Agent methodology loaded via MCP tool `get_agent`. Call `get_agent(agents: ["cloud-architect"])` to read the full methodology at delegation time.